© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 50496
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ง่าย
    -0.09
     integer
    -0.09
    -high
    -0.09
    high
    -0.08
     xor
    -0.08
    inaire
    -0.08
     high
    -0.08
    integer
    -0.08
     Euler
    -0.08
    Euler
    -0.08
    POSITIVE LOGITS
     diagnóstico
    0.10
     Diagnostic
    0.10
     диагност
    0.09
     GED
    0.09
     gráficos
    0.09
     diagnostic
    0.09
     begrij
    0.09
     הפס
    0.09
     Grafik
    0.09
     খান
    0.09
    Activations Density 0.012%

    No Known Activations